On CPU hot unplug, when parking the last kthread we'll try and schedule into idle to kill the CPU. This last schedule can (and does) trigger newidle balance because at this point the sched domains are still up because of commit: 77d1dfda0e79 ("sched/topology, cpuset: Avoid spurious/wrong domain rebuilds") Obviously pulling tasks to an already offline CPU is a bad idea, and all balancing operations _should_ be subject to cpu_active_mask, make it so. Reported-by: Thomas Gleixner Fixes: 77d1dfda0e79 ("sched/topology, cpuset: Avoid spurious/wrong domain rebuilds") Signed-off-by: Peter Zijlstra (Intel) --- kernel/sched/fair.c | 6 ++++++ 1 file changed, 6 insertions(+) --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8448,6 +8448,12 @@ static int idle_balance(struct rq *this_ this_rq->idle_stamp = rq_clock(this_rq); /* + * Do not pull tasks towards !active CPUs... + */ + if (!cpu_active(this_cpu)) + return 0; + + /* * This is OK, because current is on_cpu, which avoids it being picked * for load-balance and preemption/IRQs are still disabled avoiding * further scheduler activity on it and we're being very careful to